Model predictive maintenance system for building equipment

Abstract

A model predictive maintenance (MPM) system for building equipment includes an equipment controller configured to operate the building equipment to affect a variable state or condition in a building and an operational cost predictor configured to predict a cost of operating the building equipment over a duration of an optimization period. The MPM system includes a maintenance cost predictor configured to predict a cost of performing maintenance on the building equipment over the duration of the optimization period and an objective function optimizer configured to optimize an objective function to predict a total cost associated with the building equipment over the duration of the optimization period. The objective function includes the predicted cost of operating the building equipment and the predicted cost of performing maintenance on the building equipment.

What is claimed is: 
     
       1. A predictive maintenance system for building equipment, the predictive maintenance system comprising:
 a maintenance cost predictor configured to predict a cost of performing maintenance on the building equipment over a duration of an optimization period; 
 an operational cost predictor configured to predict a cost of operating the building equipment over the duration of the optimization period based on equipment performance of the building equipment that results from performing the maintenance on the building equipment; 
 an objective function optimizer configured to optimize an objective function to predict a total cost associated with the building equipment over the duration of the optimization period, the objective function comprising the cost of operating the building equipment and the cost of performing maintenance on the building equipment, wherein optimizing the objective function generates operating decisions for the building equipment; and 
 an equipment controller configured to control the building equipment by generating electronic control signals based on the operating decisions for the building equipment and causing the building equipment to affect a variable state or condition in a building using the electronic control signals. 
 
     
     
       2. The predictive maintenance system of  claim 1 , further comprising a capital cost predictor configured to predict a second cost of purchasing or replacing the building equipment over the duration of the optimization period;
 wherein the objective function further comprises the second cost of purchasing or replacing the building equipment. 
 
     
     
       3. The predictive maintenance system of  claim 1 , further comprising an objective function generator configured to dynamically update the objective function on a real-time basis based on closed-loop feedback from the building equipment. 
     
     
       4. The predictive maintenance system of  claim 1 , wherein the maintenance cost predictor is configured to predict the cost of performing maintenance on the building equipment as a function of a plurality of binary decision variables that indicate whether the maintenance will be performed on the building equipment during each time of the optimization period. 
     
     
       5. The predictive maintenance system of  claim 1 , wherein the operational cost predictor is configured to:
 determine an operating efficiency of the building equipment at each time step of the optimization period; and 
 predict the cost of operating the building equipment as a function of the operating efficiency at each time step of the optimization period. 
 
     
     
       6. The predictive maintenance system of  claim 1 , wherein the operational cost predictor is configured to:
 determine an initial operating efficiency of the building equipment using equipment performance information received as feedback from the building equipment; 
 identify an efficiency degradation factor defining an amount by which operating efficiency degrades between consecutive time steps of the optimization period; and 
 determine the operating efficiency of the building equipment at each time step of the optimization period using the initial operating efficiency and the efficiency degradation factor. 
 
     
     
       7. The predictive maintenance system of  claim 6 , wherein the objective function comprises a plurality of binary decision variables that indicate whether the maintenance will be performed on the building equipment during each time of the optimization period;
 wherein the operational cost predictor is configured to reset the operating efficiency of the building equipment to a post-maintenance efficiency value at each time step during which the plurality of binary decision variables indicate that the maintenance will be performed. 
 
     
     
       8. A model predictive maintenance system for building equipment, the model predictive maintenance system comprising:
 a maintenance cost predictor configured to predict a cost of performing maintenance on the building equipment over a duration of an optimization period as a function of a plurality of binary decision variables that indicate whether maintenance will be performed on the building equipment during each time of the optimization period; 
 an operational cost predictor configured to predict a cost of operating the building equipment over the duration of the optimization period based on equipment performance of the building equipment that results from performing the maintenance on the building equipment; 
 an objective function optimizer configured to optimize an objective function to predict a total cost associated with the building equipment over the duration of the optimization period, the objective function comprising the cost of performing maintenance on the building equipment and the cost of operating the building equipment over the duration of the optimization period; and 
 an equipment controller configured to control the building equipment by generating electronic control based on operating decisions generated by the optimizing of the objective function and causing the building equipment to affect the variable state or condition in a building using the electronic control signals. 
 
     
     
       9. The model predictive maintenance system of  claim 8 , wherein the maintenance cost predictor is configured to:
 determine a reliability of the building equipment at each time step of the optimization period using equipment performance information received as feedback from the building equipment; and 
 determine values for the plurality of binary decision variables based on the reliability of the building equipment at each time step of the optimization period. 
 
     
     
       10. The model predictive maintenance system of  claim 8 , further comprising a capital cost predictor configured to predict a second cost of purchasing or replacing the building equipment over the duration of the optimization period;
 wherein the objective function further comprises the second cost of purchasing or replacing the building equipment. 
 
     
     
       11. The model predictive maintenance system of  claim 8 , wherein the operational cost predictor is configured to predict the cost of operating the building equipment over the duration of the optimization period as a function of the plurality of binary decision variables. 
     
     
       12. The model predictive maintenance system of  claim 11 , wherein the operational cost predictor is configured to:
 determine an operating efficiency of the building equipment at each time step of the optimization period; and 
 predict the cost of operating the building equipment as a function of the operating efficiency at each time step of the optimization period. 
 
     
     
       13. The model predictive maintenance system of  claim 11 , wherein the operational cost predictor is configured to:
 determine an initial operating efficiency of the building equipment using equipment performance information received as feedback from the building equipment; 
 identify an efficiency degradation factor defining an amount by which operating efficiency degrades between consecutive time steps of the optimization period; and 
 determine the operating efficiency of the building equipment at each time step of the optimization period using the initial operating efficiency and the efficiency degradation factor. 
 
     
     
       14. The model predictive maintenance system of  claim 13 , wherein the operational cost predictor is configured to reset the operating efficiency of the building equipment to a post-maintenance efficiency value at each time step during which the plurality of binary decision variables indicate that the maintenance will be performed. 
     
     
       15. A model predictive maintenance system for building equipment, the model predictive maintenance system comprising:
 a maintenance cost predictor configured to predict a cost of performing maintenance on the building equipment over a duration of an optimization period; 
 an operational cost predictor configured to predict a cost of operating the building equipment over the duration of the optimization period based on equipment performance of the building equipment that results from performing the maintenance on the building equipment; 
 an objective function optimizer configured to optimize an objective function to determine an optimal strategy for operating and maintaining the building equipment over the duration of the optimization period, the objective function comprising the cost of operating the building equipment and the cost of performing maintenance on the building equipment, wherein optimizing the objective function generates operating decisions for the building equipment; and 
 an equipment controller configured to electronically control the building equipment using the operating decisions for the building equipment such that the building equipment affects a variable state or condition in a building. 
 
     
     
       16. The model predictive maintenance system of  claim 15 , wherein:
 the operational cost predictor is configured to predict the cost of operating the building equipment as a function of a predicted energy consumption of the building equipment during each time step of the optimization period; and 
 the maintenance cost predictor is configured to predict the cost of performing maintenance on the building equipment as a function of a plurality of binary decision variables that indicate whether the maintenance will be performed on the building equipment during each time of the optimization period; and 
 the objective function optimizer is configured to optimize the objective function to determine optimal values for the plurality of binary decision variables. 
 
     
     
       17. The model predictive maintenance system of  claim 16 , wherein the operational cost predictor is configured to:
 determine an operating efficiency of the building equipment at each time step of the optimization period; and 
 predict the predicted energy consumption of the building equipment during each time step of the optimization period as a function of the operating efficiency at each time step of the optimization period. 
 
     
     
       18. The model predictive maintenance system of  claim 16 , wherein the operational cost predictor is configured to:
 determine an initial operating efficiency of the building equipment using equipment performance information received as feedback from the building equipment; 
 identify an efficiency degradation factor defining an amount by which operating efficiency degrades between consecutive time steps of the optimization period; and 
 determine the operating efficiency of the building equipment at each time step of the optimization period using the initial operating efficiency and the efficiency degradation factor. 
 
     
     
       19. The model predictive maintenance system of  claim 18 , wherein the operational cost predictor is configured to reset the operating efficiency of the building equipment to a post-maintenance efficiency value at each time step during which the plurality of binary decision variables indicate that the maintenance will be performed. 
     
     
       20. The model predictive maintenance system of  claim 16 , further comprising a capital cost predictor configured to predict a second cost of purchasing or replacing the building equipment over the duration of the optimization period;
 wherein the objective function further comprises the second cost of purchasing or replacing the building equipment.